© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 111134
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    The
    -0.07
    ствуют
    -0.07
     खुले
    -0.07
     statues
    -0.07
    7
    -0.07
    1
    -0.07
     investigation
    -0.07
    Investig
    -0.07
     grace
    -0.07
     освоб
    -0.07
    POSITIVE LOGITS
     multiplication
    0.11
     Multiply
    0.11
     multiplying
    0.10
     multiply
    0.10
     multiplied
    0.10
    multiply
    0.10
    乘
    0.10
     千
    0.10
    Multiply
    0.09
    chwan
    0.09
    Activations Density 0.036%

    No Known Activations